Canvas LMS
Connects Canvas LMS to AI assistants, enabling users to list courses and retrieve assignment details through natural language. It features secure multi-institution support with encrypted token storage and a simplified setup process for students.
What is Canvas LMS?
Canvas LMS is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to connects canvas lms to ai assistants, enabling users to list courses and retrieve assignment details through natural language. it features secure multi-institution support with encrypted token storage...
Connects Canvas LMS to AI assistants, enabling users to list courses and retrieve assignment details through natural language. It features secure multi-institution support with encrypted token storage and a simplified setup process for students.
This server falls under the Business Applications category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- Connects Canvas LMS to AI assistants, enabling users to list
Use Cases
Maintainer
Works with
Installation
PIP
pip install canvas-mcpManual Installation
pip install canvas-mcpConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Canvas LMS
Canvas MCP Server is a Python package that connects Canvas LMS to AI assistants through the Model Context Protocol, exposing over 90 tools covering course management, assignment tracking, grading, discussions, and accessibility auditing. Students can ask natural language questions like 'What is due this week?' while educators can bulk-grade submissions, run WCAG accessibility scans, and manage course content — all from within Claude Desktop or other MCP clients. It supports secure multi-institution use with encrypted token storage and includes FERPA-compliant data anonymization for educators who need to discuss student data without exposing PII.
Prerequisites
- Python 3.10 or newer
- A Canvas API token (generate one in Canvas under Account > Settings > Approved Integrations > New Access Token)
- Your institution's Canvas API base URL (e.g. https://canvas.instructure.com)
- An MCP-compatible client such as Claude Desktop, Cursor, or Zed
- pip or pipx for installation
Install the canvas-mcp package
Install the package from PyPI using pip. It is recommended to use a virtual environment to avoid dependency conflicts.
python3 -m venv .venv
source .venv/bin/activate # Windows: .venv\Scripts\activate
pip install canvas-mcpConfigure your Canvas API credentials
Create a .env file in your project directory with your Canvas API token and institution URL. You can copy the provided template if you cloned the repository.
CANVAS_API_TOKEN=your_canvas_api_token_here
CANVAS_API_URL=https://your-institution.instructure.comVerify the Canvas connection
Run the built-in test command to confirm the server can reach your Canvas instance and authenticate successfully before configuring your MCP client.
canvas-mcp-server --testConfigure your MCP client
Add the Canvas MCP server to your Claude Desktop configuration. Use the absolute path to the virtual environment's binary to ensure the correct Python environment is used.
{
"mcpServers": {
"canvas": {
"command": "/absolute/path/to/.venv/bin/canvas-mcp-server"
}
}
}Optional: enable FERPA data anonymization for educator use
If you are an instructor who needs to discuss student data with AI tools, enable the anonymization feature so PII is redacted from responses automatically.
ENABLE_DATA_ANONYMIZATION=trueCanvas LMS Examples
Client configuration
Claude Desktop configuration for the Canvas MCP server installed in a virtual environment.
{
"mcpServers": {
"canvas": {
"command": "/Users/yourname/canvas-mcp/.venv/bin/canvas-mcp-server",
"env": {
"CANVAS_API_TOKEN": "your_canvas_api_token",
"CANVAS_API_URL": "https://your-institution.instructure.com"
}
}
}
}Prompts to try
Natural language prompts for students and educators using Canvas MCP with Claude.
- "What assignments are due this week across all my courses?"
- "Show me my current grades in all active courses"
- "List all unread announcements in my Canvas courses"
- "Who hasn't submitted Assignment 3 in CS101?"
- "Run an accessibility audit on the Introduction to Python course modules"
- "Generate a summary of discussion posts in the Week 2 forum"Troubleshooting Canvas LMS
Authentication fails with 401 Unauthorized when testing the connection
Double-check your CANVAS_API_TOKEN value — it should be the full token string generated from Canvas Settings, not your login password. Also verify that CANVAS_API_URL does not have a trailing slash and matches your institution's exact domain.
Canvas API rate limit errors appear during bulk operations
Canvas enforces approximately 700 requests per 10 minutes. For bulk grading or large course operations, use the execute_typescript tool with max_concurrent=5 to batch requests, or space out operations across multiple prompts.
Claude Desktop does not start the server or shows an empty tool list
Ensure you are using the absolute path to the canvas-mcp-server binary inside your virtual environment, not a relative path. Run `which canvas-mcp-server` with the venv activated to find the correct path. Relative paths and PATH-dependent commands often fail in Claude Desktop's execution environment.
Frequently Asked Questions about Canvas LMS
What is Canvas LMS?
Canvas LMS is a Model Context Protocol (MCP) server that connects canvas lms to ai assistants, enabling users to list courses and retrieve assignment details through natural language. it features secure multi-institution support with encrypted token storage and a simplified setup process for students. It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Canvas LMS?
Install via pip with: pip install canvas-mcp. Then configure your AI client to connect to this MCP server.
Which AI clients work with Canvas LMS?
Canvas LMS works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Canvas LMS free to use?
Yes, Canvas LMS is open source and available under the MIT license. You can use it freely in both personal and commercial projects.
Canvas LMS Alternatives — Similar Business Applications Servers
Looking for alternatives to Canvas LMS? Here are other popular business applications servers you can use with Claude, Cursor, and VS Code.
n8n
★ 189.1kA comprehensive MCP server that provides full control over n8n automation workflows through natural language. It offers 43 tools for managing workflows, executions, credentials, and data tables, with safety features like write-mode protection and dou
LobeHub
★ 77.5k🤯 LobeHub is your Chief Agent Operator, organizing your agents into 7×24 operations by hiring, scheduling, and reporting on your entire AI team.
Jeecgboot
★ 46.4kAI 低代码平台，「低代码 + 零代码」双模式驱动：低代码一键生成前后端代码，零代码 5 分钟搭建系统，AI Skills 一句话画流程、设计表单、生成整套系统。内置 AI聊天、知识库、流程编排、MCP插件等，兼容主流大模型。引领「AI 生成 → 在线配置 → 代码生成 → 手工合并->AI修改」开发模式，消除 Java 项目 80% 的重复工作，提效而不失灵活。
CowAgent
★ 44.7kCowAgent (chatgpt-on-wechat) 是基于大模型的超级AI助理，能主动思考和任务规划、访问操作系统和外部资源、创造和执行Skills、通过长期记忆和知识库不断成长，比OpenClaw更轻量和便捷。同时支持微信、飞书、钉钉、企微、QQ、公众号、网页等接入，可选择DeepSeek/OpenAI/Claude/Gemini/ MiniMax/Qwen/GLM/LinkAI，能处理文本、语音、图片和文件，可快速搭建个人AI助理和企业数字员工。
Minds Platform
★ 39.2kPlatform dedicated to building an open foundation for applied Artificial Intelligence, designed for people seeking production-ready AI systems they can truly control, extend and deploy anywhere.
Astrbot
★ 32.8kAI Agent Assistant & development framework that integrates lots of IM platforms, LLMs, plugins and AI feature, and can be your openclaw alternative. ✨
Browse More Business Applications MCP Servers
Explore all business applications servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up Canvas LMS in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use Canvas LMS?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.